A weighing data acquisition and analysis system and method based on industrial Internet of Things

Abstract

The present invention relates to the field of highway overweight control technology, and specifically to a weighing data acquisition and analysis system and process based on the industrial Internet of Things, comprising: a control terminal, an acquisition layer, an analysis layer and a marking layer; the control terminal is the main control end of the system, and is used to issue an execution command; the weight of a truck is dynamically acquired in real time through the acquisition layer, and the acquisition layer synchronously acquires a moving image of the truck, and the acquired moving image of the truck is segmented based on a dynamic acquisition timestamp of the truck weight. The present invention brings highway overweight control management to large trucks by combining dynamic weighing equipment with static weighing equipment. In the process of weighing large trucks, the collection of truck image data is introduced at the same time, and the driving speed of the truck during the dynamic weighing process is analyzed, so as to reflect the accuracy of the dynamic weighing result of the truck, and further based on the accuracy of the dynamic weighing result, a decision is made whether to apply the static weighing equipment to weigh the truck again, so as to determine whether the truck is overweight.

Description

Technical Field

[0001] The present invention relates to the technical field of highway overload control, and in particular to a weighing data acquisition and analysis system and process based on industrial Internet of Things. Background Art

[0002] Highway overload control refers to the control of overloading of highway freight vehicles.

[0003] Dynamic weighing refers to weighing a vehicle while it is moving, while static weighing refers to weighing the vehicle when it is stationary. Dynamic weighing and static weighing are two commonly used technologies for highway overload control.

[0004] However, in the process of highway overload control, there are many factors that affect the inaccurate weighing results of weighing equipment. It is obviously impossible to completely eliminate the weighing error of weighing equipment.

[0005] Therefore, currently, technical personnel are often committed to the research and development of the accuracy of weighing results of weighing equipment, but have not paid much attention to the research and development of related technologies on how to more simply determine whether a vehicle is overweight.

[0006] To this end, we proposed a weighing data acquisition and analysis system and process based on industrial Internet of Things. Summary of the invention

[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides a weighing data acquisition and analysis system and process based on industrial Internet of Things, which solves the technical problems raised in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] In the first aspect, a weighing data collection and analysis system based on the industrial Internet of Things includes: a control terminal, a collection layer, an analysis layer and a marking layer;

[0010] The control terminal is the main control terminal of the system and is used to issue execution commands;

[0011] The weight of the truck is collected dynamically in real time through the collection layer. The collection layer collects the moving images of the truck synchronously. Based on the dynamic collection timestamp of the truck weight, the collected moving images of the truck are segmented, and the truck image is extracted synchronously from the moving images of the truck. The distance between each row of wheels of the truck in the truck image is identified. The analysis layer synchronously receives the segmentation results of the moving images of the truck and the recognition results of the distance between each row of wheels of the truck. The accuracy of the dynamic weighing results of the truck is analyzed by combining the segmentation results and the recognition results. Further, based on the accuracy analysis results, it is determined whether the truck is overweight. The marking layer receives the determination results of whether the truck is overweight in real time, and decides whether to mark the truck based on the determination results.

[0012] The analysis layer includes a receiving module, an analysis module, a verification module and a determination module. The receiving module is used to receive the truck moving image segmentation results obtained by the collection layer and the identification results of the distance between each row of wheels of the truck. The analysis module is used to traverse the truck moving image segmentation results and the identification results of the distance between each row of wheels of the truck received by the receiving module, and identify the accuracy of the truck dynamic weighing results based on the truck moving image segmentation results and the identification results of the distance between each row of wheels of the truck. The verification module is used to receive the accuracy of the truck dynamic weighing results and the truck dynamic weighing results analyzed by the analysis module, and verify the truck dynamic weighing results based on the accuracy analysis results of the truck dynamic weighing results. The determination module is used to receive the verification results of the truck dynamic weighing results in the verification module, and determine whether the truck is overweight based on the verification results of the truck dynamic weighing results.

[0013] The accuracy analysis logic of the truck dynamic weighing results in the analysis module is expressed as follows:

[0014]

[0015] Where: T is the accuracy judgment value of the dynamic weighing result of the truck; m is the total amount of moving image segmentation of the truck; d j is the moving distance of the truck corresponding to the j-th truck moving image; t j is the time of moving images of the jth group of trucks; The maximum ratio of the truck moving distance corresponding to the truck moving image to the truck moving image time; is the minimum ratio of the truck moving distance to the truck moving time corresponding to the truck moving image; g max is the maximum weighing value of the dynamic weighing equipment; g min It is the minimum weighing value of the dynamic weighing equipment;

[0016] The larger the accuracy judgment value T of the dynamic weighing result of the truck is, the lower the accuracy of the dynamic weighing result of the truck is; conversely, the higher the accuracy of the dynamic weighing result of the truck is.

[0017] The weight of the truck is collected by dynamic weighing equipment and static weighing equipment. A group of dynamic weighing equipment and static weighing equipment are respectively set at the entrance and exit of the truck weighing section. When the truck enters the weighing section, the dynamic weighing equipment is used to dynamically collect the weight of the truck.

[0018] Furthermore, the acquisition layer includes a weighing module, a camera module and a recognition module. The weighing module is used to collect the weight of each row of wheels of the truck, and obtain the weight of the truck based on the accumulated collected weight. The camera module is used to collect moving images of the truck, and synchronously obtain the timestamp of the weighing module when collecting the weight of each row of wheels of the truck. Based on the timestamp, the moving images of the truck are segmented. The recognition module is used to receive the moving images of the truck collected by the camera module, extract the truck image from the moving images of the truck, and recognize the distance between adjacent rows of wheels of the truck in the truck image based on the truck image.

[0019] Among them, the weighing module is integrated by the dynamic weighing device and the static weighing device. When the weighing module is controlled by the acquisition layer, the dynamic weighing device is used to dynamically weigh the truck. The truck has no less than three rows of wheels. When each row of truck wheels is completely on the surface of the dynamic weighing device, the dynamic weighing device dynamically weighs the weight of the row of wheels. The weight of the truck is expressed as:

[0020]

[0021] Where: G is the weight of the truck; n is the number of weighing times of the dynamic weighing equipment; g i The dynamic weighing device weighs the weight of a row of truck wheels for the i-th time.

[0022] Furthermore, when the camera module performs segmentation processing on the truck moving image, the timestamp of each dynamic weighing of the dynamic weighing device is used as the segmentation target, and the truck moving image data is segmented with the timestamp in the truck moving image that is the same as the segmentation target, and the sub-truck moving images obtained by each segmentation are arranged based on the time sequence, and the first group of sub-truck moving images and the last group of sub-truck moving images in each group of sub-truck moving images arranged based on the time sequence are discarded;

[0023] The camera module is deployed on one side of the road where the truck is traveling, and the truck moving image acquisition direction of the camera module is perpendicular to the side surface of the truck.

[0024] Furthermore, during the operation phase of the recognition module, the truck image is extracted from the truck moving image based on the background subtraction algorithm, and the lowest point of each wheel image area is further captured on the boundary of the truck image, and the actual distance between each group of adjacent capture points is calculated, that is:

[0025]

[0026] Where: d is the actual distance between two sets of adjacent capture points; d′ is the distance between two sets of adjacent capture points in the truck image; D is the distance between the camera end of the camera module and the truck wheel; f is the focal length of the camera module;

[0027] In each group of capture points sorted based on the forward direction of the truck, the actual distance between each two adjacent groups of capture points is recorded as d1, d2, d3, ..., that is, the distance between each row of wheels of the truck recognized by the recognition module.

[0028] Furthermore, in the accuracy analysis logic of the truck dynamic weighing result:

[0029]

[0030] Furthermore, the verification logic for the dynamic weighing result in the verification module is:

[0031]

[0032] Where: G UP is the upper limit of the dynamic weighing result; q is the total number of wheels in the truck; G DOWN It is the lower limit value of dynamic weighing result;

[0033] Among them, G DOWN If both G and the truck weight exceed the overweight judgment value of the road section where the truck is located, the truck is judged to be overweight, and G UP If both G and L do not exceed the overweight judgment value of the road section where the truck is located, the truck is judged to be not overweight;

[0034] Anyway, the result of determining whether the truck is overweight is considered ambiguous.

[0035] Furthermore, the marking layer includes a marking module and a guiding module. The marking module is used to obtain the judgment result of whether the truck is overweight in the analysis layer, and mark the truck image collected by the monitoring equipment on the truck weighing section corresponding to the truck whose judgment result is fuzzy. The guiding module is used to guide the truck to be weighed by the static weighing equipment at the exit position of the truck weighing section;

[0036] Among them, the monitoring equipment and the marking module on the truck weighing section interact in real time based on the wireless network. When the judgment result of whether the truck is overweight is ambiguous, the monitoring equipment sends the image of the corresponding truck to the marking module. The marking module further marks and stores the truck image. The marking content is text information such as "truck to be tested". The marking module synchronizes the marking content of the truck image with the dynamic weighing result of the corresponding truck.

[0037] Furthermore, the monitoring device closest to the exit of the truck weighing section collects the image of the truck heading for the exit of the truck weighing section in real time, and compares the similarity with each marked truck image stored in the marking module in real time. When a marked truck image with a similarity greater than 90% is compared, the guiding module is triggered to run;

[0038] The guiding module is integrated with arrow-shaped LED lights, which point to the static weighing equipment deployed at the exit of the truck weighing section. The overweight judgment of the truck weighed by the static weighing equipment shall be based on the weighing result of the static weighing equipment.

[0039] Furthermore, the receiving module is interactively connected to the analysis module, the verification module and the judgment module through a wireless network, the receiving module is interactively connected to the identification module through a wireless network, the identification module is interactively connected to the weighing module and the camera module through a wireless network, the weighing module is interactively connected to the control terminal through a wireless network, the judgment module is interactively connected to the marking module through a wireless network, and the marking module is interactively connected to the guiding module through a wireless network.

[0040] In the second aspect, a weighing data collection and analysis process based on the industrial Internet of Things includes the following steps:

[0041] Step 1: Deploy dynamic weighing equipment, static weighing equipment and cameras at the entrance and exit of the truck weighing section;

[0042] Step 2: When a truck enters the truck weighing section entrance, a dynamic weighing device is used to collect the truck weight, and a camera is used to collect the moving image of the truck simultaneously;

[0043] Step 3: Segment the truck moving image according to the number of times the truck dynamic weighing equipment collects the truck weight and the response collection timestamp;

[0044] Step 4: extract the truck image from the collected truck moving image data, synchronously identify the bottom point of each wheel image area in the truck image, calculate the distance between each adjacent point, and record it as the distance between each row of adjacent wheels of the truck;

[0045] Step 5: Use the truck moving image segmentation results and the distance ratio between adjacent wheels of each row of trucks to analyze the accuracy of the dynamic weighing results of the trucks;

[0046] Step 6: Based on the accuracy analysis result of the dynamic weighing result of the truck, the truck weighing limit is estimated, and whether the truck is overweight is determined according to the estimated truck weighing limit;

[0047] Step 7: Decide whether to perform static weighing on the truck based on the determination result.

[0048] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0049] The present invention provides a weighing data collection and analysis system based on the industrial Internet of Things. During operation, the system brings highway overweight control to large trucks by combining dynamic weighing equipment with static weighing equipment. During the weighing of large trucks, the collection of truck image data is introduced at the same time, and the driving speed of the truck during the dynamic weighing process is analyzed, so as to reflect the accuracy of the dynamic weighing result of the truck. Further, based on the accuracy of the dynamic weighing result, it is decided whether to use the static weighing equipment to weigh the truck again, so as to determine whether the truck is overweight. Therefore, without fully considering the dynamic weighing accuracy, a simpler, faster and more targeted overweight determination is made for the truck.

[0050] At the same time, based on a weighing data collection and analysis process based on the industrial Internet of Things, further operation logic support is provided for the above system to ensure the stable operation of the above system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 It is a structural diagram of a weighing data acquisition and analysis system based on industrial Internet of Things;

[0053] Figure 2 It is a flow chart of a weighing data collection and analysis process based on the industrial Internet of Things;

[0054] Figure 3 This is a schematic diagram of the dynamic weighing process of a truck in the present invention;

[0055] Figure 4 This is a schematic diagram of the distance between each row of wheels of a truck identified by the identification module of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] The present invention will be further described below in conjunction with the embodiments.

[0058] Embodiment 1:

[0059] A weighing data collection and analysis system based on industrial Internet of Things in this embodiment, such as Figure 1 As shown, it includes: control terminal, collection layer, analysis layer and marking layer;

[0060] The control terminal is the main control terminal of the system and is used to issue execution commands;

[0061] The weight of the truck is collected dynamically in real time through the collection layer. The collection layer collects the moving images of the truck synchronously. Based on the dynamic collection timestamp of the truck weight, the collected moving images of the truck are segmented, and the truck image is extracted synchronously from the moving images of the truck. The distance between each row of wheels of the truck in the truck image is identified. The analysis layer synchronously receives the segmentation results of the moving images of the truck and the recognition results of the distance between each row of wheels of the truck. The accuracy of the dynamic weighing results of the truck is analyzed by combining the segmentation results and the recognition results. Further, based on the accuracy analysis results, it is determined whether the truck is overweight. The marking layer receives the determination results of whether the truck is overweight in real time, and decides whether to mark the truck based on the determination results.

[0062] The acquisition layer includes a weighing module, a camera module and a recognition module. The weighing module is used to collect the weight of each row of wheels of the truck, and obtain the weight of the truck based on the accumulated collected weight. The camera module is used to collect the moving image of the truck, and synchronously obtain the timestamp of the weighing module when collecting the weight of each row of wheels of the truck. Based on the timestamp, the moving image of the truck is segmented. The recognition module is used to receive the moving image of the truck collected by the camera module, extract the truck image from the moving image of the truck, and recognize the distance between adjacent rows of wheels of the truck in the truck image based on the truck image.

[0063] Among them, the weighing module is integrated by the dynamic weighing device and the static weighing device. When the weighing module is controlled by the acquisition layer, the dynamic weighing device is used to dynamically weigh the truck. The truck has no less than three rows of wheels. When each row of truck wheels is completely on the surface of the dynamic weighing device, the dynamic weighing device dynamically weighs the weight of the row of wheels. The weight of the truck is expressed as:

[0064]

[0065] Where: G is the weight of the truck; n is the number of weighing times of the dynamic weighing equipment; g i The dynamic weighing device weighs the weight of a row of truck wheels for the i-th time;

[0066] The analysis layer includes a receiving module, an analysis module, a verification module and a determination module. The receiving module is used to receive the truck moving image segmentation results obtained by the collection layer and the identification results of the distance between each row of wheels of the truck. The analysis module is used to traverse the truck moving image segmentation results and the identification results of the distance between each row of wheels of the truck received by the receiving module, and identify the accuracy of the truck dynamic weighing results based on the truck moving image segmentation results and the identification results of the distance between each row of wheels of the truck. The verification module is used to receive the accuracy of the truck dynamic weighing results and the truck dynamic weighing results analyzed by the analysis module, and verify the truck dynamic weighing results based on the accuracy analysis results of the truck dynamic weighing results. The determination module is used to receive the verification results of the truck dynamic weighing results in the verification module, and determine whether the truck is overweight based on the verification results of the truck dynamic weighing results.

[0067] The accuracy analysis logic of the truck dynamic weighing results in the analysis module is expressed as:

[0068]

[0069] Where: T is the accuracy judgment value of the dynamic weighing result of the truck; m is the total amount of moving image segmentation of the truck; d j is the moving distance of the truck corresponding to the j-th truck moving image; t j is the time of moving images of the jth group of trucks; The maximum ratio of the truck moving distance corresponding to the truck moving image to the truck moving image time; is the minimum ratio of the truck moving distance to the truck moving time corresponding to the truck moving image; g max is the maximum weighing value of the dynamic weighing equipment; g min It is the minimum weighing value of the dynamic weighing equipment;

[0070] The larger the accuracy judgment value T of the dynamic weighing result of the truck is, the lower the accuracy of the dynamic weighing result of the truck is; conversely, the higher the accuracy of the dynamic weighing result of the truck is.

[0071] The marking layer includes a marking module and a guiding module. The marking module is used to obtain the judgment result of whether the truck is overweight in the analysis layer, and mark the truck image collected by the monitoring equipment on the truck weighing section corresponding to the truck whose judgment result is fuzzy. The guiding module is used to guide the truck to be weighed by the static weighing equipment at the exit of the truck weighing section.

[0072] Among them, the monitoring equipment and the marking module on the truck weighing section interact in real time based on the wireless network. When the result of determining whether the truck is overweight is fuzzy, the monitoring equipment sends the image of the corresponding truck to the marking module, and the marking module further marks and stores the truck image. The marking content is text information such as "truck to be tested". The marking module synchronizes the marking content of the truck image with the dynamic weighing result of the corresponding truck.

[0073] The weight of the truck is collected by dynamic weighing equipment and static weighing equipment. A group of dynamic weighing equipment and static weighing equipment are respectively set at the entrance and exit of the truck weighing section. When the truck enters the weighing section, the dynamic weighing equipment is used to dynamically collect the weight of the truck;

[0074] The receiving module is interactively connected to the analysis module, the verification module and the judgment module through a wireless network, the receiving module is interactively connected to the identification module through a wireless network, the identification module is interactively connected to the weighing module and the camera module through a wireless network, the weighing module is interactively connected to the control terminal through a wireless network, the judgment module is interactively connected to the marking module through a wireless network, and the marking module is interactively connected to the guidance module through a wireless network.

[0075] In this embodiment, the weighing module is operated to collect the weight of each row of wheel positions of the truck, and the weight of the truck is calculated based on the accumulated collected weights. The camera module collects the moving image of the truck, and synchronously obtains the timestamp of the weighing module collecting the weight of each row of wheel positions of the truck. The moving image of the truck is segmented based on the timestamp. The recognition module receives the moving image of the truck collected by the camera module in real time, extracts the truck image from the moving image of the truck, and recognizes the distance between adjacent rows of wheels of the truck in the truck image based on the truck image. The receiving module further receives the segmentation result of the moving image of the truck obtained by the operation of the acquisition layer, and the recognition result of the distance between each row of wheels of the truck. The analysis module is post-operated to traverse the segmentation result of the moving image of the truck and the recognition result of the distance between each row of wheels of the truck received by the receiving module. The moving image segmentation results and the recognition results of the distance between each row of wheels of the truck identify the accuracy of the dynamic weighing results of the truck. The verification module then receives the accuracy of the dynamic weighing results of the truck and the dynamic weighing results of the truck analyzed by the analysis module, and verifies the dynamic weighing results of the truck based on the accuracy analysis results of the dynamic weighing results of the truck. The judgment module further receives the verification results of the dynamic weighing results of the truck in the verification module, and determines whether the truck is overweight based on the verification results of the dynamic weighing results of the truck. Finally, the marking module obtains the judgment result of whether the truck is overweight in the analysis layer, and marks the truck image collected by the monitoring equipment on the truck weighing section for the truck whose judgment result is fuzzy. The guidance module runs to guide the truck to be weighed using the static weighing equipment at the exit of the truck weighing section.

[0076] Through the operation of the system in the above embodiment, a faster, simpler and more targeted overweight management is provided for highway overweight control, so that highway overweight control is no longer completely dependent on the accuracy improvement of weighing equipment, thus bringing safety maintenance to highway management.

[0077] Embodiment 2:

[0078] In terms of specific implementation, based on Example 1, this example refers to Figure 1 The weighing data collection and analysis system based on the industrial Internet of Things in Example 1 is further described in detail:

[0079] When the camera module performs segmentation processing on the truck moving image, the timestamp of each dynamic weighing of the dynamic weighing equipment is used as the segmentation target, and the truck moving image data is segmented with the timestamp in the truck moving image that is the same as the segmentation target. The sub-truck moving images obtained by each segmentation are arranged based on the time sequence, and the first group of sub-truck moving images and the last group of sub-truck moving images in each group of sub-truck moving images arranged based on the time sequence are discarded;

[0080] The camera module is deployed on one side of the road where the truck is traveling, and the truck moving image acquisition direction of the camera module is perpendicular to the side surface of the truck;

[0081] During the operation phase of the recognition module, the truck image is extracted from the moving image of the truck based on the background subtraction algorithm. The lowest point of each wheel image area is further captured on the boundary of the truck image, and the actual distance between each group of adjacent capture points is calculated, that is:

[0082]

[0083] Where: d is the actual distance between two sets of adjacent capture points; d′ is the distance between two sets of adjacent capture points in the truck image; D is the distance between the camera end of the camera module and the truck wheel; f is the focal length of the camera module;

[0084] In each group of capture points sorted based on the forward direction of the truck, the actual distance between each two adjacent groups of capture points is recorded as d1, d2, d3, ..., that is, the distance between each row of wheels of the truck recognized by the recognition module.

[0085] Through the above settings, operation logic support is further provided for the operation of the collection layer of the system in Example 1, ensuring the stable operation of the collection layer and providing necessary operation data support for the subsequent analysis layer operation.

[0086] like Figure 1 As shown in the figure, the accuracy analysis logic of the dynamic weighing results of trucks is as follows:

[0087]

[0088] The above logic formula is used to define the accuracy analysis logic of the truck dynamic weighing results used in Example 1.

[0089] like Figure 1 As shown in the figure, the verification logic for dynamic weighing results in the verification module is:

[0090]

[0091] Where: G UP is the upper limit of the dynamic weighing result; q is the total number of wheels in the truck; G DOWN It is the lower limit value of dynamic weighing result;

[0092] Among them, G DOWN If both G and the truck weight exceed the overweight judgment value of the road section where the truck is located, the truck is judged to be overweight, and G UP If both G and L do not exceed the overweight judgment value of the road section where the truck is located, the truck is judged to be not overweight;

[0093] Anyway, the result of determining whether the truck is overweight is considered ambiguous.

[0094] Through the above settings, the verification logic of the dynamic weighing result of the verification module of the system in Example 1 is limited, providing further operation logic support for the operation of the marking layer.

[0095] like Figure 1 As shown, the monitoring device closest to the exit of the truck weighing section collects the image of the truck heading to the exit of the truck weighing section in real time, and compares the similarity with each marked truck image stored in the marking module in real time. When a marked truck image with a similarity greater than 90% is compared, the guiding module is triggered to run;

[0096] The guidance module is integrated with arrow-shaped LED lights, which point to the static weighing equipment deployed at the exit of the truck weighing section. The overweight judgment of the truck weighed by the static weighing equipment shall be based on the weighing result of the static weighing equipment.

[0097] Through the above settings, the operation logic is further limited for the module operation in the marking layer, and the specific structure of the guide module is limited, ensuring the complete operation of the technical solution based on the system as the carrier provided in Example 1.

[0098] Embodiment 3:

[0099] In terms of specific implementation, based on Example 1, this example refers to Figure 2 The weighing data collection and analysis system based on the industrial Internet of Things in Example 1 is further described in detail:

[0100] A weighing data collection and analysis process based on industrial Internet of Things includes the following steps:

[0101] Step 1: Deploy dynamic weighing equipment, static weighing equipment and cameras at the entrance and exit of the truck weighing section;

[0102] Step 2: When a truck enters the truck weighing section entrance, a dynamic weighing device is used to collect the truck weight, and a camera is used to collect the moving image of the truck simultaneously;

[0103] Step 3: Segment the truck moving image according to the number of times the truck dynamic weighing equipment collects the truck weight and the response collection timestamp;

[0104] Step 4: extract the truck image from the collected truck moving image data, synchronously identify the bottom point of each wheel image area in the truck image, calculate the distance between each adjacent point, and record it as the distance between each row of adjacent wheels of the truck;

[0105] Step 5: Use the truck moving image segmentation results and the distance ratio between adjacent wheels of each row of trucks to analyze the accuracy of the dynamic weighing results of the trucks;

[0106] Step 6: Based on the accuracy analysis result of the dynamic weighing result of the truck, the truck weighing limit is estimated, and whether the truck is overweight is determined according to the estimated truck weighing limit;

[0107] Step 7: Decide whether to perform static weighing on the truck based on the determination result.

[0108] In summary, in the above embodiment, during operation, the system brings highway overweight control to large trucks by combining dynamic weighing equipment with static weighing equipment. In the process of weighing large trucks, the collection of truck image data is introduced at the same time, and the driving speed of the truck during the dynamic weighing process is analyzed, so as to reflect the accuracy of the dynamic weighing results of the truck. Further, based on the accuracy of the dynamic weighing results, it is decided whether to use the static weighing equipment to weigh the truck again, so as to determine whether the truck is overweight. Therefore, without fully considering the accuracy of dynamic weighing, a simpler, faster and more targeted overweight judgment of the truck is made.

[0109] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A weighing data acquisition and analysis system based on industrial Internet of Things, characterized in that: include: Control terminal, collection layer, analysis layer and marking layer; The control terminal is the main control terminal of the system and is used to issue execution commands; The weight of the truck is collected dynamically in real time through the collection layer. The collection layer collects the moving images of the truck synchronously. Based on the dynamic collection timestamp of the truck weight, the collected moving images of the truck are segmented, and the truck image is extracted synchronously from the moving images of the truck. The distance between each row of wheels of the truck in the truck image is identified. The analysis layer synchronously receives the segmentation results of the moving images of the truck and the recognition results of the distance between each row of wheels of the truck. The accuracy of the dynamic weighing results of the truck is analyzed by combining the segmentation results and the recognition results. Further, based on the accuracy analysis results, it is determined whether the truck is overweight. The marking layer receives the determination results of whether the truck is overweight in real time, and decides whether to mark the truck based on the determination results. The analysis layer includes a receiving module, an analysis module, a verification module and a determination module. The receiving module is used to receive the truck moving image segmentation results obtained by the collection layer and the identification results of the distance between each row of wheels of the truck. The analysis module is used to traverse the truck moving image segmentation results and the identification results of the distance between each row of wheels of the truck received by the receiving module, and identify the accuracy of the truck dynamic weighing results based on the truck moving image segmentation results and the identification results of the distance between each row of wheels of the truck. The verification module is used to receive the accuracy of the truck dynamic weighing results and the truck dynamic weighing results analyzed by the analysis module, and verify the truck dynamic weighing results based on the accuracy analysis results of the truck dynamic weighing results. The determination module is used to receive the verification results of the truck dynamic weighing results in the verification module, and determine whether the truck is overweight based on the verification results of the truck dynamic weighing results. The accuracy analysis logic of the truck dynamic weighing results in the analysis module is expressed as follows: Where: T is the accuracy judgment value of the dynamic weighing result of the truck; m is the total amount of moving image segmentation of the truck; d j is the moving distance of the truck corresponding to the j-th truck moving image; t j is the time of moving images of the jth group of trucks; The maximum ratio of the truck moving distance corresponding to the truck moving image to the truck moving image time; is the minimum ratio of the truck moving distance to the truck moving time corresponding to the truck moving image; g max is the maximum weighing value of the dynamic weighing equipment; g min It is the minimum weighing value of the dynamic weighing equipment; The larger the accuracy judgment value T of the dynamic weighing result of the truck is, the lower the accuracy of the dynamic weighing result of the truck is; conversely, the higher the accuracy of the dynamic weighing result of the truck is. The weight of the truck is collected by a dynamic weighing device and a static weighing device. A group of dynamic weighing devices and static weighing devices are respectively provided at the entrance and exit of the truck weighing section. When the truck enters the weighing section, the dynamic weighing device is used to dynamically collect the weight of the truck; The acquisition layer includes a weighing module, a camera module and a recognition module. The weighing module is used to collect the weight of each row of wheels of the truck, and obtain the weight of the truck based on the accumulated collected weight. The camera module is used to collect moving images of the truck, synchronously obtain the timestamp of the weighing module when collecting the weight of each row of wheels of the truck, and segment the moving images of the truck based on the timestamp. The recognition module is used to receive the moving images of the truck collected by the camera module, extract the truck image from the moving images of the truck, and recognize the distance between adjacent rows of wheels of the truck in the truck image based on the truck image. Among them, the weighing module is integrated by the dynamic weighing device and the static weighing device. When the weighing module is controlled by the acquisition layer, the dynamic weighing device is used to dynamically weigh the truck. The truck has no less than three rows of wheels. When each row of truck wheels is completely on the surface of the dynamic weighing device, the dynamic weighing device dynamically weighs the weight of the row of wheels. The weight of the truck is expressed as: Where: G is the weight of the truck; n is the number of weighing times of the dynamic weighing equipment; g i The dynamic weighing device weighs the weight of a row of truck wheels for the i-th time; When the camera module performs segmentation processing on the truck moving image, the timestamp of each dynamic weighing of the dynamic weighing device is used as the segmentation target, and the truck moving data is segmented with the timestamp in the truck moving image that is the same as the segmentation target, and the sub-truck moving images obtained by each segmentation are arranged based on the time sequence, and the first group of sub-truck moving images and the last group of sub-truck moving images in each group of sub-truck moving images arranged based on the time sequence are discarded; The camera module is deployed on one side of the road where the truck is traveling, and the truck moving image acquisition direction of the camera module is perpendicular to the side surface of the truck; During the operation phase of the recognition module, the truck image is extracted from the truck moving image based on the background subtraction algorithm, and the lowest point of each wheel image area is further captured on the boundary of the truck image, and the actual distance between each group of adjacent capture points is calculated, that is: Where: d is the actual distance between two sets of adjacent capture points; d′ is the distance between two sets of adjacent capture points in the truck image; D is the distance between the camera end of the camera module and the truck wheel; f is the focal length of the camera module; Then, in each group of capture points sorted based on the forward direction of the truck, the actual distance between each two adjacent groups of capture points is recorded as d1, d2, d3, ..., that is, the distance between each row of wheels of the truck identified by the recognition module; In the accuracy analysis logic of the truck dynamic weighing results: The verification logic for the dynamic weighing result in the verification module is: Where: G UP is the upper limit of the dynamic weighing result; q is the total number of wheels in the truck; G DOWN It is the lower limit value of dynamic weighing result; Among them, G DOWN If both G and the truck weight exceed the overweight judgment value of the road section where the truck is located, the truck is judged to be overweight, and G UP If both G and R do not exceed the overweight judgment value of the road section where the truck is located, the truck is judged to be not overweight; Otherwise, the result of determining whether the truck is overweight is considered to be in an ambiguous state; The marking layer includes a marking module and a guiding module. The marking module is used to obtain the judgment result of whether the truck is overweight in the analysis layer, and mark the truck image collected by the monitoring equipment on the truck weighing section corresponding to the truck whose judgment result is fuzzy. The guiding module is used to guide the truck to be weighed by the static weighing equipment at the exit position of the truck weighing section; Among them, the monitoring equipment and the marking module on the truck weighing section interact in real time based on the wireless network. When the result of determining whether the truck is overweight is fuzzy, the monitoring equipment sends the image of the corresponding truck to the marking module, and the marking module further marks and stores the truck image. The marking content is text information such as "truck to be tested". The marking module synchronously configures the marking content of the truck image with the dynamic weighing result of the corresponding truck. The monitoring equipment closest to the exit of the truck weighing section collects the image of the truck heading to the exit of the truck weighing section in real time, and compares the similarity with the marked truck images stored in the marking module in real time. When the marked truck image with a similarity greater than 90% is compared, the guiding module is triggered to run; The guiding module is integrated with arrow-shaped LED lights, which point to the static weighing equipment deployed at the exit of the truck weighing section. The overweight judgment of the truck weighed by the static weighing equipment shall be based on the weighing result of the static weighing equipment.

2. The weighing data acquisition and analysis system based on industrial Internet of Things according to claim 1 is characterized in that: The receiving module is interactively connected to the analysis module, the verification module and the determination module through a wireless network, the receiving module is interactively connected to the identification module through a wireless network, the identification module is interactively connected to the weighing module and the camera module through a wireless network, the weighing module is interactively connected to the control terminal through a wireless network, the determination module is interactively connected to the marking module through a wireless network, and the marking module is interactively connected to the guidance module through a wireless network.

3. A weighing data collection and analysis method based on the industrial Internet of Things, the method is an implementation method of a weighing data collection and analysis system based on the industrial Internet of Things as claimed in claim 2, characterized in that: The following steps are involved: Step 1: Deploy dynamic weighing equipment, static weighing equipment and cameras at the entrance and exit of the truck weighing section; Step 2: When a truck enters the truck weighing section entrance, a dynamic weighing device is used to collect the truck weight, and a camera is used to collect the moving image of the truck simultaneously; Step 3: Segment the truck moving image according to the number of times the truck dynamic weighing equipment collects the truck weight and the response collection timestamp; Step 4: extract the truck image from the collected truck moving image data, synchronously identify the bottom point of each wheel image area in the truck image, calculate the distance between each adjacent point, and record it as the distance between each row of adjacent wheels of the truck; Step 5: Use the truck moving image segmentation results and the distance ratio between adjacent wheels of each row of trucks to analyze the accuracy of the dynamic weighing results of the trucks; Step 6: Based on the accuracy analysis result of the dynamic weighing result of the truck, the truck weighing limit is estimated, and whether the truck is overweight is determined according to the estimated truck weighing limit; Step 7: Decide whether to perform static weighing on the truck based on the determination result.

Images